Topic generation for a publication

Abstract

An aspect of topic generation includes parsing communications conducted by users through an application. The communications include a communication generated by a sender and response communications received from recipients in reply to the communication generated by the sender. An aspect also includes identifying keywords, timestamps, and indications of sentiment from the parsed communications through natural language processing, determining a focus of the communication generated by the sender based on the keywords identified from the parsing, and formulating a topic for a publication based on criteria including a frequency of occurrence of the keywords in the parsed communications, a threshold level of the indications of sentiment that appear in the parsed communications, and/or a number of the communications containing one or more of the keywords having corresponding timestamps that fall within a threshold period of time. An aspect further includes submitting the topic for publication to the sender.

What is claimed is: 
     
       1. A method, comprising:
 parsing, by a work-load optimized computing, network communications conducted among users through a plurality of different network-based communication applications, wherein the network communications comprise a dialog-based communication generated by a sender and dialog-based response communications received from recipients in reply to the communication generated by the sender; 
 identifying keywords and indications of sentiment from the parsed communications through natural language processing by the work-load optimized computing system, wherein the indications of sentiment are identified from the dialog-based response communications and reflect a reaction to content expressed in the dialog-based communication generated by the sender; 
 determining a focus of the communication generated by the sender based on the keywords identified from the parsing; 
 formulating for display, by a topic generator application, a topic for a publication based on criteria including a frequency of occurrence of one or more of the keywords in the parsed communications, a threshold level of the indications of sentiment that appear in the parsed communications, and a number of the communications containing one or more of the keywords, wherein the indications of sentiment include emoticons and pre-defined terms and phrases that express emotion; 
 displaying as selectable the topic in response to formulation of the topic for publication based on the threshold level of the indications of sentiment including emoticons and pre-defined terms and phrases that express emotion; and 
 in response to selecting the topic, submitting, via the work-load optimized computing system, the topic for publication to a publication application server that is configured to present the topic to a user when the user logs into a publication application of the publication application server. 
 
     
     
       2. The method of  claim 1 , further comprising parsing communications conducted by the users across multiple applications, and classifying the parsed communications conducted by the users across multiple applications according to timestamp and thread. 
     
     
       3. The method of  claim 1 , further comprising:
 applying a weight to the keywords that are determined to be associated with the indications of sentiment, such that selection of the topic for publication is influenced by the keywords based on the corresponding weight. 
 
     
     
       4. The method of  claim 1 , further comprising:
 searching at least one data source for the keywords; and 
 submitting, to the user, content corresponding to results of the searching. 
 
     
     
       5. The method of  claim 1 , further comprising:
 identifying, as a result of natural language processing applied to the communications conducted by the users, content that expounds on the topic for publication; and 
 submitting, to the user, the content along with the topic for publication. 
 
     
     
       6. The method of  claim 1 , wherein the topic for publication includes a candidate subject and content for a blog that is under authorship by the user. 
     
     
       7. The method of  claim 1 , wherein the communications are conducted among the users during a course of employment and the topic for publication is submitted to the sender through the computer processor, as a workplace server of the sender. 
     
     
       8. A work-load optimized computing system, comprising:
 at least one hardware transactional memory; 
 and 
 a processing unit for executing computer readable instructions, the computer readable instructions including: 
 parsing communications conducted among users through a plurality of different network communication applications, wherein the network communications comprise a dialog-based communication generated by a sender and dialog-based response communications received from recipients in reply to the communication generated by the sender; 
 identifying keywords and indications of sentiment from the parsed communications through natural language processing, wherein the indications of sentiment are identified from the dialog-based response communications and reflect a reaction to content expressed in the dialog-based communication generated by the sender; 
 determining a focus of the communication generated by the sender based on the keywords identified from the parsing; 
 formulating for display, by a topic generator application, a topic for a publication based on criteria including a frequency of occurrence of one or more of the keywords in the parsed communications, a threshold level of the indications of sentiment that appear in the parsed communications, and a number of the communications containing one or more of the keywords, wherein the indications of sentiment include emoticons and pre-defined terms and phrases that express emotion; 
 displaying as selectable the topic in response to formulation of the topic for publication based on the threshold level of the indications of sentiment including emoticons and pre-defined terms and phrases that express emotion; and 
 in response to selecting the topic, submitting the topic for publication to a publication application server that is configured to present the topic to a user when the user logs into a publication application of the publication application server. 
 
     
     
       9. The system of  claim 8 , wherein the instructions further include parsing communications conducted by the users across multiple applications, and classifying the parsed communications conducted by the users across multiple applications according to timestamp and thread. 
     
     
       10. The system of  claim 8 , wherein the method further comprises:
 applying a weight to the keywords that are determined to be associated with the indications of sentiment, such that selection of the topic for publication is influenced by the keywords based on the corresponding weight. 
 
     
     
       11. The system of  claim 8 , wherein the instructions further include:
 searching at least one data source for the keywords; and 
 submitting, to the user, content corresponding to results of the searching. 
 
     
     
       12. The system of  claim 8 , wherein the instructions further include:
 identifying, as a result of natural language processing applied to the communications conducted by the users, content that expounds on the topic for publication; and 
 submitting, to the user, the content along with the topic for publication. 
 
     
     
       13. The system of  claim 8 , wherein the topic for publication includes a candidate subject and content for a blog that is under authorship by the user. 
     
     
       14. The system of  claim 8 , wherein the communications are conducted among the users during a course of employment and the topic for publication is submitted to the sender through the computer processor, as a workplace server of the sender. 
     
     
       15. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a work-load optimized computing system to cause the work-load optimized computing system to perform a method comprising:
 parsing communications conducted among users through a plurality of different network communication applications, the network communications comprise a dialog-based communication generated by a sender and dialog-based response communications received from recipients in reply to the communication generated by the sender; 
 identifying keywords and indications of sentiment from the parsed communications through natural language processing, wherein the indications of sentiment are identified from the dialog-based response communications and reflect a reaction to content expressed in the dialog-based communication generated by the sender; 
 determining a focus of the communication generated by the sender based on the keywords identified from the parsing; 
 formulating for display, by a topic generator application, a topic for a publication based on criteria including a frequency of occurrence of one or more of the keywords in the parsed communications, a threshold level of the indications of sentiment that appear in the parsed communications, and a number of the communications containing one or more of the keywords, wherein the indications of sentiment include emoticons and pre-defined terms and phrases that express emotion; 
 displaying as selectable the topic in response to formulation of the topic for publication based on the threshold level of the indications of sentiment including emoticons and pre-defined terms and phrases that express emotion; and 
 in response to selecting the topic, submitting the topic for publication to a publication application server that is configured to present the topic to a user when the user logs into a publication application of the publication application server. 
 
     
     
       16. The computer program product of  claim 15 , wherein the program instructions executable by the processor further cause the computer processor to perform parsing communications conducted by the users across multiple applications, and classifying the parsed communications conducted by the users across multiple applications according to timestamp and thread. 
     
     
       17. The computer program product of  claim 15 , wherein the method further comprises:
 applying a weight to the keywords that are determined to be associated with the indications of sentiment, such that selection of the topic for publication is influenced by the keywords based on the corresponding weight. 
 
     
     
       18. The computer program product of  claim 15 , wherein the program instructions executable by the processor further cause the computer processor to perform:
 searching at least one data source for the keywords; and 
 submitting, to the user, content corresponding to results of the searching. 
 
     
     
       19. The computer program product of  claim 15 , wherein the program instructions executable by the processor further cause the computer processor to perform:
 identifying, as a result of natural language processing applied to the communications conducted by the users, content that expounds on the topic for publication; and 
 submitting, to the user, the content along with the topic for publication. 
 
     
     
       20. The computer program product of  claim 15 , wherein the topic for publication includes a candidate subject and content for a blog that is under authorship by the user.